SmartBench

What is SmartBench?

SmartBench is the first benchmark specifically designed to evaluate the capabilities of on-device large language models in smartphone scenarios.

Released

2025-09-26

Modality

multimodal

Evaluates

多模态, Multimodal, Capabilities of on-device LLMs, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/SmartBench

SmartBench paper and code

• Paper https://arxiv.org/abs/2503.06029
• Code https://github.com/vivo-ai-lab/SmartBench

Which sources cite SmartBench?

• SmartBench

Related 多模态, Multimodal, Capabilities of on-device LLMs, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported benchmarks

• 3DCodeBench
• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AECBench